Skip to content

The implementation of "A Weakly-supervised Framework for COVID-19 Classification and Lesion Localization from Chest CT"

Notifications You must be signed in to change notification settings

theodoruszq/covid-19-detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

A Weakly-supervised Framework for COVID-19 Classification and Lesion Localization from Chest CT

By Xinggang Wang, Xianbo Deng, Qing Fu, Qiang Zhou, Jiapei Feng, Hui Ma, Wenyu Liu, Chuansheng Zheng.


This project aims at providing a deep learning algorithm to detect COVID-19 from chest CT using weak label. And the souce code of training and testing is provided. If you have interests about more details, please check our paper (IEEE Transactions on Medical Imaging).


Before running the code, please prepare a computer with NVIDIA GPU, then install Anaconda, PyTorch and NVIDIA CUDA driver. Once the environment and dependent libraries are installed, please check the README.md files in 2dunet and deCoVnet directories.

  • In the directory of "2dunet", the code mainly aims to segment the lung region to obtain all lung masks.

  • In the directory of "deCoVnet", the code does the classification task of whether a CT volume being infected.

  • In the directory of "lesion_loc", the code mainly implements the lesion localization.

  • The file "20200212-auc95p9.txt" contains the output probabilities of our pretrained deCovNet on our testing set.

The pretrained models are currently available at Google Drive, unet and deCoVnet.

If you have any other questions, please contact Xinggang Wang.

LICENSE

License: CC BY-NC-SA 4.0

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

You should have received a copy of the license along with this work. If not, see http://creativecommons.org/licenses/by-nc-sa/4.0/.

About

The implementation of "A Weakly-supervised Framework for COVID-19 Classification and Lesion Localization from Chest CT"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages